© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14904
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases often found together in sports articles and official reports

    oai_token-act-pair · gemini-2.0-flash

    Quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ich
    -0.50
    ic
    -0.49
    lä
    -0.46
    ik
    -0.46
    vo
    -0.45
    if
    -0.44
     ked
    -0.44
    ark
    -0.44
    1
    -0.43
    æ
    -0.43
    POSITIVE LOGITS
     Савезне
    1.09
     صوتيه
    1.05
     Мексичка
    1.05
     nahilalakip
    1.02
    __":
    0.97
    ]")]
    0.95
    InjectAttribute
    0.92
    #+#
    0.92
     autorytatywna
    0.92
     виправивши
    0.91
    Activations Density 6.855%

    No Known Activations